RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos
By Wenbin Du, Yali Wang, Yu Qiao. 2017
173 citations recorded by the source corpus.
Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
- Wanqing Li
- Pichao Wang
- Jun Liu
- Philip O. Ogunbona
- Mengyuan Liu
- Qiuhong Ke
- Hossein Rahmani
- Sergio Escalera
In Computer Vision and Pattern Recognition
- Jun Liu
- Pichao Wang
- Wanqing Li
- Philip O. Ogunbona
- G. Wang
- Hossein Rahmani
- Qiuhong Ke
- Sergio Escalera
In Human-Computer Interaction
- Pichao Wang
- Wanqing Li
- Jun Liu
- Philip O. Ogunbona
- Sergio Escalera
- Hossein Rahmani
- Jun Wan
- Mengyuan Liu
Citations in the corpus
- RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “Du et al. (2015a) represented a skeleton sequence as a matrix by concatenating the joint coordinates at each instant and arranging the vector representations in a chronological order. The matrix is then quantified into an image and normalized to handle the variable-length problem. The final image is”
- Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking (2018, background): “This section concentrates on the training process, which is also a trend for recent trackers [2, 13], because for object tracking there is limited information to train a brandnew deep model online.”
- Attention, please! A survey of neural attention models in deep learning (2021, background): “1 3 to dynamically learn the correlation between input features and output (Qin et al. 2017; Liang et al. 2018b; Du et al. 2017).”
- Recognizing Human Actions as the Evolution of Pose Estimation Maps (2018, background): “RPAN [8] goes beyond previous studies by training an end-to-end RNN network, and achieves accuracy of 97.”
- Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison (2019, methodology): “Some works [23, 10] also employ the joint locations as a guidance to extract local deep features around the joint regions.”
- PoTion: Pose MoTion Representation for Action Recognition (2018, unknown): “[9] combine an end-to-end recurrent network with a pose-attention mechanism for action recognition.”
- Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “Thus, most of the existing methods have adopted gated RNN architectures, such as Long-Short Term Memory (LSTM) [67], [68], [69], [70], to”